MetaPSICOV: combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins

Abstract

Motivation: Recent developments of statistical techniques to infer direct evolutionary couplings between residue pairs have rendered covariation-based contact prediction a viable means for accurate 3D modelling of proteins, with no information other than the sequence required. To extend the usefulness of contact prediction, we have designed a new meta-predictor (MetaPSICOV) which combines three distinct approaches for inferring covariation signals from multiple sequence alignments, considers a broad range of other sequence-derived features and, uniquely, a range of metrics which describe both the local and global quality of the input multiple sequence alignment. Finally, we use a two-stage predictor, where the second stage filters the output of the first stage. This two-stage predictor is additionally evaluated on its ability to accurately predict the long range network of hydrogen bonds, including correctly assigning the donor and acceptor residues.

Results: Using the original PSICOV benchmark set of 150 protein families, MetaPSICOV achieves a mean precision of 0.54 for top-L predicted long range contacts-around 60% higher than PSICOV, and around 40% better than CCMpred. In de novo protein structure prediction using FRAGFOLD, MetaPSICOV is able to improve the TM-scores of models by a median of 0.05 compared with PSICOV. Lastly, for predicting long range hydrogen bonding, MetaPSICOV-HB achieves a precision of 0.69 for the top-L/10 hydrogen bonds compared with just 0.26 for the baseline MetaPSICOV.

Availability and implementation: MetaPSICOV is available as a freely available web server at http://bioinf.cs.ucl.ac.uk/MetaPSICOV. Raw data (predicted contact lists and 3D models) and source code can be downloaded from http://bioinf.cs.ucl.ac.uk/downloads/MetaPSICOV.

Supplementary information: Supplementary data are available at Bioinformatics online.

Fig. 1.

Distribution of predictions for 9678 observed true contacts, as predicted by PSICOV, DCA and CCMpred. Data are the top L/2 correct contact predictions from each method (for sequence separation >=5 residues), for a set of 150 Pfam families (Jones et al., 2012)

Fig. 2.

Mean precision of contact prediction against increasing number of predicted pairs for (a) sequence separation ≥5, (b) for sequence separation ≥23 and (c) for sequence separation ≥23 with redundant contact predictions excluded (see text for details)

Fig. 3.

MetaPSICOV top-L/2 precision plotted against (a) PSICOV precision, (b) DCA precision and (c) CCMpred precision for sequence separation ≥5 (line x = y shown for reference)

Fig. 4.

All contacts (a) and long-range contacts (b) top-L/10 mean precision for alignments with varying numbers of effective sequences (N_eff)

Fig. 5.

Differences in mean TM-scores for the 150 benchmark proteins obtained by FRAGFOLD using (a) MetaPSICOV stage 1 contacts and (b) MetaPSICOV stage 2 contacts compared with PSICOV contacts